Structured Neuron Pruning in Deep Neural Networks Using Multi-Armed Bandits

• URL: http://arxiv.org/abs/2606.07615v1
• Date: Fri, 29 May 2026 19:56:54 GMT
• Title: Structured Neuron Pruning in Deep Neural Networks Using Multi-Armed Bandits
• Abstract summary: This paper develops a structured pruning framework in which complete neurons are removed using multi-armed bandit (MAB) algorithms.<n>The framework supports policies, including Epsilon-Greedy, Softmax, UCB1 and Thompson Sampling, and multiplicative-weight policies, including Hedge-style multiplicative weights and EXP3.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep neural networks often contain redundant hidden units. Removing individual weights can reduce parameter count, but unstructured sparsity is not always easy to exploit in standard dense implementations. This paper develops a structured pruning framework in which complete neurons are removed using multi-armed bandit (MAB) algorithms. Each candidate neuron is treated as an arm; pulling an arm temporarily masks that neuron, measures the change in loss on a sampled mini-batch, restores the neuron, and updates an estimate of its safe-removal reward. The framework supports stochastic policies, including Epsilon-Greedy, Softmax, UCB1 and Thompson Sampling, and multiplicative-weight policies, including Hedge-style multiplicative weights and EXP3. We evaluate the method on tabular classification, tabular regression and deep neural-network benchmarks covering image, text and reasoning tasks. Statistical comparisons using the Friedman test followed by the Nemenyi post-hoc test show significant differences between methods. On tabular classification tasks, UCB1 obtains the highest mean rank among pruning policies and improves on the unpruned neural network. On regression tasks, UCB1 obtains the highest mean rank and is statistically competitive with, or superior to, several standard regression models according to R^2. On deep-learning tasks, UCB1 and Thompson Sampling obtain the strongest ranks, and several MAB policies significantly outperform the unpruned model, magnitude-based neuron pruning and greedy activation-variation pruning. The results show that MAB-based neuron pruning is an effective and computationally practical approach for structured model reduction.

Related papers

• Doubly Robust Proxy Causal Learning with Neural Mean Embeddings [58.8808794752741]
  We develop a neural doubly robust framework for proxy causal learning with continuous and structured treatments.<n>The framework covers population, heterogeneous, and conditional dose-response functions, yielding full response-curve estimators.<n>Across synthetic and image-valued benchmarks, the proposed estimators outperform existing baselines and single-bridge neural estimators.
  arXiv  Detail & Related papers  (2026-05-10T12:50:25Z)
• Deep learning with missing data [3.829599191332801]
  We propose Pattern Embedded Neural Networks (PENNs), which can be applied in conjunction with any existing imputation technique.<n>In addition to a neural network trained on the imputed data, PENNs pass the vectors of observation indicators through a second neural network to provide a compact representation.<n>The outputs are then combined in a third neural network to produce final predictions.
  arXiv  Detail & Related papers  (2025-04-21T18:57:36Z)
• Revisiting Large Language Model Pruning using Neuron Semantic Attribution [63.62836612864512]
  We conduct evaluations on 24 datasets and 4 tasks using popular pruning methods.<n>We surprisingly find a significant performance drop of existing pruning methods in sentiment classification tasks.<n>We propose Neuron Semantic Attribution, which learns to associate each neuron with specific semantics.
  arXiv  Detail & Related papers  (2025-03-03T13:52:17Z)
• Magnificent Minified Models [0.360953887026184]
  This paper concerns itself with the task of taking a large trained neural network and 'compressing' it to be smaller by deleting parameters or entire neurons. We compare various methods of parameter and neuron selection: dropout-based neuron damage estimation, neuron merging, absolute-value based selection, random selection. For neuron-level pruning, retraining from scratch did much better in our experiments.
  arXiv  Detail & Related papers  (2023-06-16T21:00:44Z)
• Can pruning improve certified robustness of neural networks? [106.03070538582222]
  We show that neural network pruning can improve empirical robustness of deep neural networks (NNs) Our experiments show that by appropriately pruning an NN, its certified accuracy can be boosted up to 8.2% under standard training. We additionally observe the existence of certified lottery tickets that can match both standard and certified robust accuracies of the original dense models.
  arXiv  Detail & Related papers  (2022-06-15T05:48:51Z)
• Bagged Polynomial Regression and Neural Networks [0.0]
  Series and dataset regression are able to approximate the same function classes as neural networks. textitbagged regression (BPR) is an attractive alternative to neural networks. BPR performs as well as neural networks in crop classification using satellite data.
  arXiv  Detail & Related papers  (2022-05-17T19:55:56Z)
• Revisiting Gaussian Neurons for Online Clustering with Unknown Number of Clusters [0.0]
  A novel local learning rule is presented that performs online clustering with a maximum limit of the number of cluster to be found. The experimental results demonstrate stability in the learned parameters across a large number of training samples.
  arXiv  Detail & Related papers  (2022-05-02T14:01:40Z)
• Receding Neuron Importances for Structured Pruning [11.375436522599133]
  Structured pruning efficiently compresses networks by identifying and removing unimportant neurons. We introduce a simple BatchNorm variation with bounded scaling parameters, based on which we design a novel regularisation term that suppresses only neurons with low importance. We show that neural networks trained this way can be pruned to a larger extent and with less deterioration.
  arXiv  Detail & Related papers  (2022-04-13T14:08:27Z)
• Scaling Structured Inference with Randomization [64.18063627155128]
  We propose a family of dynamic programming (RDP) randomized for scaling structured models to tens of thousands of latent states. Our method is widely applicable to classical DP-based inference. It is also compatible with automatic differentiation so can be integrated with neural networks seamlessly.
  arXiv  Detail & Related papers  (2021-12-07T11:26:41Z)
• Training Feedback Spiking Neural Networks by Implicit Differentiation on the Equilibrium State [66.2457134675891]
  Spiking neural networks (SNNs) are brain-inspired models that enable energy-efficient implementation on neuromorphic hardware. Most existing methods imitate the backpropagation framework and feedforward architectures for artificial neural networks. We propose a novel training method that does not rely on the exact reverse of the forward computation.
  arXiv  Detail & Related papers  (2021-09-29T07:46:54Z)
• And/or trade-off in artificial neurons: impact on adversarial robustness [91.3755431537592]
  Presence of sufficient number of OR-like neurons in a network can lead to classification brittleness and increased vulnerability to adversarial attacks. We define AND-like neurons and propose measures to increase their proportion in the network. Experimental results on the MNIST dataset suggest that our approach holds promise as a direction for further exploration.
  arXiv  Detail & Related papers  (2021-02-15T08:19:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.